Name: Aidan Scannell
Type: User
Company: Aalto University
Bio: Postdoctoral Researcher at Aalto University | Aalto Robot Learning Lab | Machine Learning Research Group | Finnish Center for Artificial Intelligence
Twitter: scannell_aidan
Location: Helsinki, Finland
Blog: www.aidanscannell.com
Aidan Scannell's Projects
My dotfiles
My personal website powered by the Hugo Academic theme.
Implementation of agent based programming language, AgentSpeak(L)
Personal Resume
Pair your phone and stream audio to a Raspberry Pi running Volumio
This work implements and compares a variety of approximate inference techniques for the tasks of image restoration (de-noising) and image segmentation.
A status bar widget for Ubersicht on OS X
Model-based reinforcement learning in TensorFlow
Improving predictions of Bayesian neural nets via local linearization, AISTATS 2021
My personal Emacs configuration inspired by David Wilson's config, Spacemacs and Doom Emacs.
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
My personal dotfiles.
The path to GNUrvana
DrQ-v2: Improved Data-Augmented Reinforcement Learning
Flax is a neural network library for JAX that is designed for flexibility.
A toolkit for reproducible reinforcement learning research.
Minimal library for geometric machine learning in TensorFlow (and GPflow).
Gaussian processes in TensorFlow
Code for efficiently sampling functions from GP(flow) posteriors
Minimal Gaussian process library in JAX with a simple (custom) approach to state management.
Gaussian processes framework in python
Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
PyBullet Gym environments for single and multi-agent reinforcement learning of quadcopter control
Mobile manipulation research tools for roboticists
iQRL: implicitly Quantized Reinforcement Learning
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
JAX implementations of core Deep RL algorithms
This project involved developing algorithms capable of localising a robot within a known environment but at an unknown position and moving it to a target location.
Lane and vehicle detection software for an autonomous vehicle.